kernel_optimize_test/include/linux/rculist_nulls.h
Eric Dumazet d7efc6c11b net: remove hlist_nulls_add_tail_rcu()
Alexander Potapenko reported use of uninitialized memory [1]

This happens when inserting a request socket into TCP ehash,
in __sk_nulls_add_node_rcu(), since sk_reuseport is not initialized.

Bug was added by commit d894ba18d4 ("soreuseport: fix ordering for
mixed v4/v6 sockets")

Note that d296ba60d8 ("soreuseport: Resolve merge conflict for v4/v6
ordering fix") missed the opportunity to get rid of
hlist_nulls_add_tail_rcu() :

Both UDP sockets and TCP/DCCP listeners no longer use
__sk_nulls_add_node_rcu() for their hash insertion.

Since all other sockets have unique 4-tuple, the reuseport status
has no special meaning, so we can always use hlist_nulls_add_head_rcu()
for them and save few cycles/instructions.

[1]

==================================================================
BUG: KMSAN: use of uninitialized memory in inet_ehash_insert+0xd40/0x1050
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.0+ #3288
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x185/0x1d0 lib/dump_stack.c:52
 kmsan_report+0x13f/0x1c0 mm/kmsan/kmsan.c:1016
 __msan_warning_32+0x69/0xb0 mm/kmsan/kmsan_instr.c:766
 __sk_nulls_add_node_rcu ./include/net/sock.h:684
 inet_ehash_insert+0xd40/0x1050 net/ipv4/inet_hashtables.c:413
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:754
 inet_csk_reqsk_queue_hash_add+0x1cc/0x300 net/ipv4/inet_connection_sock.c:765
 tcp_conn_request+0x31e7/0x36f0 net/ipv4/tcp_input.c:6414
 tcp_v4_conn_request+0x16d/0x220 net/ipv4/tcp_ipv4.c:1314
 tcp_rcv_state_process+0x42a/0x7210 net/ipv4/tcp_input.c:5917
 tcp_v4_do_rcv+0xa6a/0xcd0 net/ipv4/tcp_ipv4.c:1483
 tcp_v4_rcv+0x3de0/0x4ab0 net/ipv4/tcp_ipv4.c:1763
 ip_local_deliver_finish+0x6bb/0xcb0 net/ipv4/ip_input.c:216
 NF_HOOK ./include/linux/netfilter.h:248
 ip_local_deliver+0x3fa/0x480 net/ipv4/ip_input.c:257
 dst_input ./include/net/dst.h:477
 ip_rcv_finish+0x6fb/0x1540 net/ipv4/ip_input.c:397
 NF_HOOK ./include/linux/netfilter.h:248
 ip_rcv+0x10f6/0x15c0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x36f6/0x3f60 net/core/dev.c:4298
 __netif_receive_skb net/core/dev.c:4336
 netif_receive_skb_internal+0x63c/0x19c0 net/core/dev.c:4497
 napi_skb_finish net/core/dev.c:4858
 napi_gro_receive+0x629/0xa50 net/core/dev.c:4889
 e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4018
 e1000_clean_rx_irq+0x1492/0x1d30
drivers/net/ethernet/intel/e1000/e1000_main.c:4474
 e1000_clean+0x43aa/0x5970 drivers/net/ethernet/intel/e1000/e1000_main.c:3819
 napi_poll net/core/dev.c:5500
 net_rx_action+0x73c/0x1820 net/core/dev.c:5566
 __do_softirq+0x4b4/0x8dd kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364
 irq_exit+0x203/0x240 kernel/softirq.c:405
 exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:638
 do_IRQ+0x15e/0x1a0 arch/x86/kernel/irq.c:263
 common_interrupt+0x86/0x86

Fixes: d894ba18d4 ("soreuseport: fix ordering for mixed v4/v6 sockets")
Fixes: d296ba60d8 ("soreuseport: Resolve merge conflict for v4/v6 ordering fix")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexander Potapenko <glider@google.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-05 18:06:09 -05:00

138 lines
4.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RCULIST_NULLS_H
#define _LINUX_RCULIST_NULLS_H
#ifdef __KERNEL__
/*
* RCU-protected list version
*/
#include <linux/list_nulls.h>
#include <linux/rcupdate.h>
/**
* hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on the node return true after this. It is
* useful for RCU based read lockfree traversal if the writer side
* must know if the list entry is still hashed or already unhashed.
*
* In particular, it means that we can not poison the forward pointers
* that may still be used for walking the hash list and we can only
* zero the pprev pointer so list_unhashed() will return true after
* this.
*
* The caller must take whatever precautions are necessary (such as
* holding appropriate locks) to avoid racing with another
* list-mutation primitive, such as hlist_nulls_add_head_rcu() or
* hlist_nulls_del_rcu(), running on this same list. However, it is
* perfectly legal to run concurrently with the _rcu list-traversal
* primitives, such as hlist_nulls_for_each_entry_rcu().
*/
static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
{
if (!hlist_nulls_unhashed(n)) {
__hlist_nulls_del(n);
n->pprev = NULL;
}
}
#define hlist_nulls_first_rcu(head) \
(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
#define hlist_nulls_next_rcu(node) \
(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
/**
* hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the hash list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry().
*/
static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
n->pprev = LIST_POISON2;
}
/**
* hlist_nulls_add_head_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_nulls,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *first = h->first;
n->next = first;
n->pprev = &h->first;
rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
if (!is_a_nulls(first))
first->pprev = &n->next;
}
/**
* hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_nulls_node within the struct.
*
* The barrier() is needed to make sure compiler doesn't cache first element [1],
* as this loop can be restarted [2]
* [1] Documentation/atomic_ops.txt around line 114
* [2] Documentation/RCU/rculist_nulls.txt around line 146
*/
#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
/**
* hlist_nulls_for_each_entry_safe -
* iterate over list of given type safe against removal of list entry
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_nulls_node within the struct.
*/
#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
#endif
#endif